convez.ai
MCP ServerSegurançaAvançado
sF1nX

x402station-mcp

sF1nX/x402station-mcp

Camada de segurança pré-voo para endpoints x402 em comércio agentic

Ver no GitHub
InicialPluginScore · de 0 a 100

MCP server que integra a camada independente de sinais de risco x402station.io para comércio agentic. Fornece verificações de segurança pré-pagamento (detecção de decoys, zumbis, armadilhas de preço) e histórico de probing de endpoints antes de assinar transações de pagamento.

Instalação

$npx convez-ai sF1nX/x402station-mcp

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
3
Forks
0
Acompanhando
0
Saúde
42%
Último commit
há 5 meses
Versão
v1.0.10
Issues abertas
7
Contribuidores
2

Casos de uso

  • Validar segurança de endpoints x402 antes de enviar pagamentos
  • Detectar endpoints fraudulentos, zumbis e armadilhas de preço
  • Gerar relatórios forenses detalhados de saúde de endpoints
  • Manter catálogo local de endpoints maliciosos conhecidos

Veredito

Ferramenta especializada e crítica para agentes que operam com pagamentos x402. Requer chave privada e USDC em Base mainnet, mas fornece proteção essencial contra fraudes em transações autônomas. Ideal para arquiteturas agentic commerce maduras.

README

A tradução para o português deste README ainda está na fila.

Glama MCP server score

x402station-mcp

MCP adapter for x402station.io, the independent risk-signal layer for x402 agentic commerce. Exposes Preflight by x402station.io plus Forensics, Catalog Decoys, Alternatives, Credits, Watch, and Whats New. Any agent speaking the Model Context Protocol gets endpoint evidence before signing PAYMENT-SIGNATURE — decoy, zombie, price-trap, never-paid, latency, signature/settlement checks — before paying.

x402station.io independently probes every endpoint listed on agentic.market every 10 minutes and merges probe history with CDP settlement data. Policy engines decide and enforce; x402station.io measures and reports. We do not route, take custody, or endorse.

Install

# Claude Code / Cursor / Windsurf / Continue — works anywhere with MCP
npm install -g x402station-mcp
# or use npx in the config, no global install needed:

Configure

The adapter charges real USDC per paid call through x402 itself. You need a wallet private key that holds Base mainnet USDC.

Claude Code

Add to ~/.claude/claude_desktop_config.json (or wherever your MCP servers live):

{
  "mcpServers": {
    "x402station": {
      "command": "npx",
      "args": ["-y", "x402station-mcp"],
      "env": {
        "AGENT_PRIVATE_KEY": "0xYOUR_PRIVATE_KEY_HERE"
      }
    }
  }
}

Cursor / Windsurf / Continue

Same shape — every MCP host understands command / args / env. See your tool's MCP docs.

Environment

VariableRequiredDefaultPurpose
AGENT_PRIVATE_KEYyes for any paid tool call—0x-prefixed 64-hex-char private key. Account must hold Base mainnet USDC.
X402STATION_BASE_URLnohttps://x402station.ioOverride for dev / testing.

Tools

preflight(url) — $0.001 USDC

Ask whether it's safe to pay this x402 URL. Returns:

{
  "ok": true,
  "warnings": [],
  "metadata": {
    "service": "...",
    "price_usdc": "0.01",
    "uptime_1h_pct": 100,
    "avg_latency_ms": 412
  }
}

ok is true only when no critical warning fires. Warnings include unknown_endpoint, no_history, dead, zombie, decoy_price_extreme, never_paid_zombie, proxy_markup, wildcard_402, spa_fallback, suspicious_high_price, slow, and new_provider.

forensics(url) — $0.001 USDC

Deep 7-day report. Superset of preflight. Returns hourly uptime, latency p50/p90/p99, status-code distribution, concentration-group stats, decoy probability. Extra warnings: dead_7d, mostly_dead, slow_p99, price_outlier_high, high_concentration.

catalog_decoys() — $0.005 USDC

Full blacklist. Returns every active endpoint currently flagged critical, plus per-reason counts. Pull periodically and cache locally — cheaper than preflighting every URL.

Typical agent flow

agent wants data from some_endpoint.com
    │
    ├─ preflight("https://some_endpoint.com/data")  ← $0.001
    │     ok: false, warnings: ["decoy_price_extreme"]
    │
    └─ skip; try the next candidate

For bulk discovery, do catalog_decoys() once per day and treat the result as a set-difference against any URLs you're about to hit.

Composes with

x402station checks whether the endpoint is safe (decoy / zombie / price-trap / never-paid) before an agent pays. It pairs naturally with a payload safety check — screening the payment metadata for PII before signing:

agent intent: pay some_endpoint.com
    ├─ x402station    preflight(url)              ← is the ENDPOINT safe?
    ├─ presidio-x402  screen_payment_metadata()   ← is the PAYLOAD safe?
    └─ pay()

presidio-hardened-x402-mcp screens payment metadata for PII before signing. The two servers are developed independently, on purpose — keeping the signals uncorrelated is the point. This is a composition pointer, not an endorsement; see their repo for the screening tool's behaviour and limits.

Links

Contact

License

MIT

Ver o original no GitHub

Bom para

Relacionados